Browser UseUse JSON Schema to define the target data structure and apply it to all websites. For static pages, get clean page text (Markdown) and let the LLM fill the Schema. Only use a browser proxy for pages that require login, clicking, or JavaScript flow.
Baseten BlogBDN has released the Sealed Volumes feature, allowing users to publish model data once and mount it in any deployment, solving the data drift problem caused by model files lacking a single data source. This feature archives directories, Hugging Face repositories, S3/GCS, and other data sources as immutable versions, managing files through content hash keys, eliminating the need for repeated downloads during deployment.
LangChain Blog5858LangChain's internal agents integrate with Slack to execute tasks as a user or with fixed credentials, featuring global and user-level memory, executing code in a sandbox, and supporting background scheduling. Its architecture includes three agents: GTM, OpenSWE, and Content Studio, which handle GTM activities, engineering code reviews, and marketing content creation, respectively. The 'breakout' feature optimizes user experience and addresses core issues like authentication.
Databricks BlogDatabricks AI Search now natively supports Streaming Tables, Materialized Views, and Managed tables using Iceberg v3+, except for Delta tables.
Cognition Blog6060Cognition launches Devin Security product, which provides deep scanning through Claude Mythos and other cutting-edge network models, allowing enterprises to use these features without needing separate access to the models.
PyTorch Blog3434Nemotron 3.5 achieved the highest streaming speech recognition accuracy on Google Pixel 11 using ExecuTorch and SME2, reaching up to 11.7% WER (with 1,120 ms audio blocks and QC8W precision), which is 3.5x faster than FP32 but with increased latency; shorter audio blocks (e.g., 80 ms) can reduce latency but accuracy drops to 15.2% WER.
Latent Space4242Supabase plans to run long-running workloads alongside its database using Supabase Compute, simplify schemas to make them easier for AI agents to understand, and design infrastructure that supports more applications. Its acquired Turso product supports scaling, and the company is using AI internally to improve efficiency while maintaining a parallel approach of open-source and commercial sales.
AWS Machine Learning Blog3838Amazon SageMaker SDK v3 released, training anomaly detectors and defect classifiers for each camera through dual-branch SageMaker Pipelines, and setting quality gates to prevent underperforming models.
AWS Machine Learning Blog4848Building enterprise-grade intelligent retrieval on Amazon Bedrock knowledge base using AWS CDK, providing multi-round planning and tool-driven retrieval through the reasoning agent and AgenticRetrieveStream API, returning referenced answers. The solution deployment includes a CDK application with Amazon S3 corpus, knowledge base, and reasoning agent, supporting semantic routing and multiple retrievals, and built-in Amazon CloudWatch monitoring and evaluation features.
Sierra Blog6565Sierra is now available on Google Cloud Marketplace, enabling businesses to leverage existing Google Cloud commitments to partner with Sierra. Through Sierra, businesses can build and deploy AI agents to improve customer experience and drive business growth, from loan refinancing to paying insurance claims or preventing customer churn.
MarkTechPost5858Nace AI releases Drex for Search, a retrieval layer for document search, with its decision model Drex achieving 92.05% accuracy in the BrowseComp-Plus evaluation, using only 12.6 search calls per query. Supports CLI, SDK, MCP, or REST calls, and can be paired with response models like GPT-5, Gemini 3.5 Flash, or Qwen 27B, ranking top two in the 3/4 public leaderboard.
Meta Engineering5858Meta shared network innovations at the 2026 OCP Global Summit to support its latest AI models Muse Wonder and Muse Spark and Prometheus clusters.
NVIDIA Technical Blog3838NVIDIA Mission Control 2.5 Released, Bringing Self-Recovery Functionality to Kubernetes. This version significantly improves fault repair efficiency by automating monitoring to optimize the resilience and availability of thousands of GPU clusters.
OpenAI News4545Fanatics uses OpenAI's Shop the Look feature to let fans complete game-day outfits, testing about 30,000 MLB products showing a 10% increase in engagement.
Oracle Launches Intelligent Agent AI Platform Oracle AI Success Navigator, Adds Six Types of AI Agents for Environmental Analysis, Application Design, Configuration Development, Testing, System Integration, and Innovation Opportunity Identification, Helping Customers Reduce Manual Operations and Simplify Complex Tasks; Medical Institution Lexington Health Reduced Some Design and Configuration Workloads by 80% with This Platform
IBM Research Blog5858IBM and the PyTorch Foundation announce that Spyre accelerator will become the first-class backend for PyTorch and support multi-accelerator scheduling. The torch-spyre compiler, Spyre vLLM plugin, and continuous integration efforts enable models and workflows to run on Spyre, an architecture optimized for inference, suitable for IBM Z, LinuxONE, and Power systems.
Wuwenshinqiong and Three-Body Universe have released the Zhizi Agent 1.0, an AI dialogue Agent with the role anchor of the 637th micro-universe administrator, achieving role consistency and interaction continuity through the AgentWorks platform, supporting cross-session memory, and relying on multi-agent collaborative mechanisms to ensure character and knowledge constraints. It adopts the PDD cross-cluster heterogeneous inference architecture to reduce the first Token latency by 51.5%.
Hugging Face Daily Papers4949RSIHub is an open-source framework that standardizes research on agent evolution by providing reusable components and a consistent evaluation infrastructure, used to build, compare, and extend related methods. Researchers can focus on evolutionary strategies while keeping evaluation external, with results associated with candidates and evaluation conditions.
Mastra Blog6565Mastra applies the corporate knowledge graph Knowledge to internal Q&A by deploying an agent in Slack, improving code generation quality; the tool integrates team collaboration system information, supports functional zoning and permission control, and has been cooperated with by multiple enterprises, now opening to more design partners.
Factory News6565The Factory Deployment Team delves into the real software environment of customers to solve the challenges of deploying autonomous agents, transforming engineering autonomy into corporate results through practices in companies like Blackstone and Nvidia. The team deploys agents on customer-owned infrastructure, achieving reasoning capabilities across large single codebases, and developing reusable product features such as code review and security review. The team is composed of highly autonomous engineering leaders responsible for strategic customer deployments and validating agent automation capabilities.
Gigabyte introduces the WRX90 AI TOP workstation motherboard, featuring a Socket sTR5 socket and E-ATX form factor, equipped with 8-channel DDR5 RDIMM slots supporting 2TB memory, including 6 PCIe Gen5 x16, 1 PCIe Gen5 x8 slot, and 2 MCIO 8i. The motherboard integrates the ASPEED AST2600 BMC SoC, supporting IPMI remote management.
The DecoderFeatured7171Anthropic indicates that a single context-loaded agent is often superior to a multi-sub-agent architecture in terms of quality, cost, and latency, and releases a migration toolkit to help teams evaluate whether to merge sub-agents. Anthropic claims that new models starting from Opus 4.5 can directly manage complex plans in a single loop, with a single-agent architecture running about twice as fast as a multi-agent solution in a single comparison.
Why it matters: Anthropic based on enterprise deployment experience gives a judgment that a single agent is better than multiple sub-agents, and lists the applicable boundaries and migration paths.
Alibaba's AI agent 'Qwen Go!' launches 'My Applications' feature, allowing users to build applications for life, work, and study scenarios without programming, supporting sharing and continuous data updates. This feature integrates with Alibaba Cloud's AI application production platform Meoo (Instant Enlightenment), which can automatically complete application setup, database configuration, and deployment. Combined with Qwen Go's cloud-based Pro capabilities, it generates more personalized tools after authorization by accessing user personal data from Taobao, Gaode, and other platforms.
Qianli Technology releases AI millimeter-wave radar integrated with a 10 TOPS NPU, achieving internal target detection and classification for the first time, supporting edge-side, satellite, and three-compatible operating modes. This radar introduces data-driven models at the front end of the perception chain to break through the rule limits of traditional architectures, shortening response times and enhancing security. Through the acquisition of Ronggan Technology, Qianli Technology has closed the soft-hard integrated business loop, realizing joint optimization of self-developed algorithms and hardware.
MarkTechPostFeatured8080Microsoft Research has open-sourced Agensh, a multi-agent framework without a central orchestrator, where each worker independently claims sub-tasks, shares discoveries, and merges code into the same Git repository.
Why it matters: The original text provides scalability data for multi-agent frameworks without a central orchestrator on ProgramBench from 1 to 1024 agents, allowing for comparison with existing orchestration solutions.
MarkTechPost6060Cognition has released a free, open-source Devin Vulnerability Fixes plugin, containing three skills to fix three critical remote code execution (RCE) vulnerabilities in PHP2Shell, Node.js, and GitLab CVE-2026-110264.
The open-source project GPU Unlock, developed by GitHub user Zagitta, can remove the instruction emission rate limit of Ampere architecture consumer-grade GPUs in FP16/BF16 tensor core operations without modifying the driver or flashing VBIOS.
Why it matters: The original text provides measured improvement data for multiple RTX 30 GPUs under GEMM and image generation workloads, also indicating limitations such as memory bandwidth.
vLLM BlogFeatured6060The vLLM team used P/D separation and Wide-EP to serve DeepSeek-V4.1-Flash on a single NVIDIA GB300 NVL72 rack, achieving 954K tokens/s per GPU and 196 tokens/s for single-user P90 on SemiAnalysis AgentX, which is 7.9 times the early single-node results.
Why it matters: The vLLM team has released per-item optimization and measured data for serving DeepSeek-V4.1-Flash on GB300 NVL72, which can be compared with DeepSeek's own engine DeepInfer.
TechCrunch · AIBlock releases Dessa speech model, which is fully trained on human speech and can run locally on consumer-grade GPUs, supports speaking and listening simultaneously, acquires knowledge through real dialogue data, expresses human emotions including laughter, pauses, and crying, currently not publicly accessible, the company is recruiting security researchers to test.
MarkTechPost6868Anthropic's open-source sandbox-runtime (srt) limits process file and network access without containers; supports macOS/Linux (Windows alpha), in the form of CLI/TS libraries, Apache-2.0 license, Node.js 22.12+, Anthropic internal testing reduced Claude Code permission prompts by 84%.
Huawei Mate 90 series phones launch the all-new XMAGE imaging service, with the gallery upgraded to support AI one-click video creation and 3D dynamic photo features.
Cohere Blog5858Cohere Model Vault introduced confidential computing on Microsoft Azure using NVIDIA GPUs in its public test version, designed to reduce the plaintext data infrastructure customers must trust and provide cryptographic evidence for customers to verify before sensitive information is released. The system protects the computation itself through hardware-enforced isolation, uses Oblivious HTTP to encrypt sensitive request content, and employs a remote attestation mechanism to ensure the environment processing requests meets expectations, thereby protecting the entire process from request transmission to computation execution.
SemiAnalysisAmazon Trainium has significantly improved its training experience with native PyTorch, enhancing its competitiveness in the training field. Trainium3 supports the standard PyTorch API, allowing most PyTorch code to be migrated to .to('neuron') without XLA annotations, but the BF16 training experience is still not fully refined. SemiAnalysis's engineering team testing shows its performance is close to the CUDA ecosystem, but there is still room for improvement.
vLLM BlogFeatured6262vLLM team releases the second part of GLM-5.3 optimization, deploying on 16 H200s with 1 pre-filled node and 1 decoding node, using PCP to split pre-fill by token and DCP to split KV cache by token, allowing 1M context to fit into the pre-fill node
Why it matters: The vLLM team has dissected how PCP, DCP, and Hybrid HiSparse can be combined on 16 H200s, allowing readers to understand the memory and pre-fetch bottlenecks of long-context deployment.
Databricks Blog2222Databricks Integrating Spark Structured Streaming Real-Time Mode, Lakebase Postgres, and Databricks Apps
Databricks Blog5858Spark's declarative pipelines are 34 times faster than imperative pipelines in 22 data engineering tasks, halve the code volume, and have fewer errors. Declarative pipelines capture structural errors in advance through pre-execution validation and offload repetitive tasks like sorting and result saving to Spark, while imperative pipelines need to run on the cluster until the error step to detect them. The two methods perform equally in terms of logical error rates, but declarative pipelines have more concise and consistent code, making them easier to maintain.
Google ResearchFeatured6262Google Research introduced the path of its tuberculosis screening AI from research to clinical use at IDWeek 2026: publishing a benchmark in Radiology in 2019, completing multi-center prospective validation in NEJM AI in 2024, and then converting it into a clinical tool certified by CE MDR Class IIb through Nexus AI.
Why it matters: Google Research outlined the complete path from imaging benchmark to CE certification tool to open-source MedGemma, allowing readers to understand the stages medical AI needs to cross to move from papers to clinical use.
iFlytek released the Xingchen TaaS platform, which transforms Token consumption into business value such as simultaneous interpretation translation and digital employees through intermediate capabilities like model scheduling and intelligent agent engines. It provides solutions for industries such as enterprise services, finance, and healthcare, ensuring that Tokens are not wasted. The Spark X2.6 edge model is open-sourced, with an expanded context window to 1 million Tokens and an edge-cloud routing accuracy of 96.1%.
LangChain Deep Agents releases3535deepagents-code 0.2.1 released, default Anthropic Auto classifier set to Claude Sonnet 5.5, new skill range MCP tool support added.
